Shape assembly, the process of combining parts into a complete whole, is a crucial skill for robots with broad real-world applications. Among the various assembly tasks, geometric assembly—where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)—is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods.

Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding; however, they still struggle with spatial understanding, which is fundamental to embodied AI. In this paper, we propose SpatialBot, a model designed to enhance spatial understanding by utilizing both RGB and depth images. To train VLMs for depth perception, we introduce the SpatialQA and SpatialQA$\boldsymbol{E}$datasets, which include multi-level depth-related questions spanning various scenarios and embodiment tasks. SpatialBench is also developed to comprehensively evaluate VLMs' spatial understanding capabilities across different levels. Extensive experiments on our spatial-understanding benchmark, general VLM benchmarks, and embodied AI tasks demonstrate the remarkable improvements offered by SpatialBot. The model, code, and datasets are available at https://github.com/BAAI-DCAI/SpatialBot.

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges: category-level ambiguity and instance-level complexity. Category-level ambiguity arises from representing objects of fine-grained categories in a highly sparse point cloud format, making category distinction challenging. Instance-level complexity stems from multiple instances of the same category coexisting in a scene, leading to distractions during grounding. To address these challenges, we propose a novel weaklysupervised grounding approach that explicitly differentiates between categories and instances. In the category-level branch, we utilize extensive category knowledge from a pre-trained external detector to align object proposal features with sentencelevel category features, thereby enhancing category awareness. In the instance-level branch, we utilize spatial relationship descriptions from language queries to refine object proposal features, ensuring clear differentiation among objects. These designs enable our model to accurately identify target-category objects while distinguishing instances within the same category. Compared to previous methods, our approach achieves state-of-the-art performance on three widely used benchmarks: Nr3D, Sr3D, and ScanRef.

Recent advancements in imitation learning have shown promising results in robotic manipulation, driven by the availability of high-quality training data. To improve data collection efficiency, some approaches focus on developing specialized teleoperation devices for robot control, while others directly use human hand demonstrations to obtain training data. However, the former requires both a robotic system and a skilled operator, limiting scalability, while the latter faces challenges in aligning the visual gap between human hand demonstrations and the deployed robot observations. To address this, we propose a human hand data collection system combined with our hand-to-gripper generative model, which translates human hand demonstrations into robot gripper demonstrations, effectively bridging the observation gap. Specifically, a GoPro fisheye camera is mounted on the human wrist to capture human hand demonstrations. We then train a generative model on a self-collected dataset of paired human hand and UMI gripper demonstrations, which have been processed using a tailored data pre-processing strategy to ensure alignment in both timestamps and observations. Therefore, given only human hand demonstrations, we are able to automatically extract the corresponding SE(3) actions and integrate them with high-quality generated robot demonstrations through our generation pipeline for training robotic policy model. In experiments, the robust manipulation performance demonstrates not only the quality of the generated robot demonstrations but also the efficiency and practicality of our data collection method. More demonstrations can be found at: https://rwor.github.io/.

Visual actionable affordance has emerged as a transformative approach in robotics, focusing on perceiving interaction areas prior to manipulation. Traditional methods rely on pixel sampling to identify successful interaction samples or processing pointclouds for affordance mapping. However, these approaches are computationally intensive and struggle to adapt to diverse and dynamic environments. This paper introduces ManipGPT, a framework designed to predict optimal interaction areas for articulated objects using a large pretrained vision transformer (ViT). We create a dataset of 9.9k simulated and real images to bridge the visual simto-real gap and enhance real-world applicability. By finetuning the vision transformer on this small dataset, we significantly improve part-level affordance segmentation, adapting the model’s in-context segmentation capabilities to robot manipulation scenarios. This enables effective manipulation across simulated and real-world environments by generating part-level affordance masks, paired with an impedance adaptation policy, sufficiently eliminating the need for complex datasets or perception systems. Our project page is available at: https://lxkim814.github.io/ManipGPT_website/

Recent advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion approaches address these challenges, they suffer from setup complexity or limited observation information utilization. To address this, leveraging the power of single-view 3D object reconstruction approaches, we propose a training-free framework SR3D that enables robotic grasping of transparent and specular objects from a single-view observation. Specifically, given single-view RGB and depth images, SR3D first uses the external visual models to generate 3D reconstructed object mesh based on RGB image. Then, the key idea is to determine the 3D object’s pose and scale to accurately localize the reconstructed object back into its original depth corrupted 3D scene. Therefore, we propose view matching and keypoint matching mechanisms, which leverage both the 2D and 3D’s inherent semantic and geometric information in the observation to determine the object’s 3D state within the scene, thereby reconstructing an accurate 3D depth map for effective grasp detection. Experiments in both simulation and real-world show the reconstruction effectiveness of SR3D. More demonstrations can be found at: https://sites.google.com/view/sr3dtech/

Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the common-sense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches have been proposed to leverage a VLM-based System 2 module for handling high-level decision-making, and a separate System 1 action module for ensuring real-time control. However, existing designs maintain both systems as separate models, limiting System 1 from fully leveraging the rich pretrained knowledge from the VLM-based System 2. In this work, we propose Fast-in-Slow (FiS), a unified dual-system vision-language-action (VLA) model that embeds the System 1 execution module within the VLM-based System 2 by partially sharing parameters. This innovative paradigm not only enables high-frequency execution in System 1, but also facilitates coordination between multimodal reasoning and execution components within a single foundation model of System 2. Given their fundamentally distinct roles within FiS-VLA, we design the two systems to incorporate heterogeneous modality inputs alongside asynchronous operating frequencies, enabling both fast and precise manipulation. To enable coordination between the two systems, a dual-aware co-training strategy is proposed that equips System 1 with action generation capabilities while preserving System 2’s contextual understanding to provide stable latent conditions for System 1. For evaluation, FiS-VLA outperforms previous state-of-the-art methods by 8% in simulation and 11% in real-world tasks in terms of average success rate, while achieving a 117.7 Hz control frequency with action chunk set to eight. Project web page: https://fast-in-slow.github.io.

Robot manipulation relies on accurately predicting contact points and end-effector directions to ensure successful operation. However, learning-based robot manipulation, trained on a limited category within a simulator, often struggles to achieve generalizability, especially when confronted with extensive categories. Therefore, we introduce an innovative approach for robot manipulation that leverages the robust reasoning capabilities of Multimodal Large Language Models (MLLMs) to enhance the stability and generalization of manipulation. By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation. The fundamental insight lies in the introduced fine-tuning paradigm, encompassing object category understanding, affordance prior reasoning, and object-centric pose prediction to stimulate the reasoning ability of MLLM in manipulation. During inference, our approach utilizes an RGB image and text prompt to predict the end effector's pose in chain of thoughts. After the initial contact is established, an active impedance adaptation policy is introduced to plan the upcoming way-points in a closed-loop manner. Moreover, in real world, we design a test-time adaptation (TTA) strategy for manipulation to enable the model better adapt to the current real-world scene configuration. Experiments in simulator and real-world show the promising performance of Mani-pLLM. More details and demonstrations can be found at https://sites.google.com/view/manipllm.

Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two commonly used modalities in visual-based robotic manipulation, but each of these modalities have their own limitations. Commercial point-cloud observations often suffer from issues like sparse sampling and noisy output due to the limits of the emission-reception imaging principle. On the other hand, RGB images, while rich in texture information, lack essential depth and 3D information crucial for robotic manipulation. To mitigate these challenges, we propose an image-only robotic manipulation framework that leverages an eye-on-hand monocular camera installed on the robot’s parallel gripper. By moving with the robot gripper, this camera gains the ability to actively perceive the object from multiple perspectives during the manipulation process. This enables the estimation of 6D object poses, which can be utilized for manipulation. While, obtaining images from more and diverse viewpoints typically improves pose estimation, it also increases the manipulation time. To address this trade-off, we employ a reinforcement learning policy to synchronize the manipulation strategy with active perception, achieving a balance between 6D pose accuracy and manipulation efficiency. Our experimental results in both simulated and real-world environments showcase the state-of-the-art effectiveness of our approach. We believe that our method will inspire further research on real-world-oriented robotic manipulation. See https://rgbmanip.github.io/ for more details.

Vision-centric bird-eye-view (BEV) perception has shown promising potential in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the challenges when facing environment changing, resulting in severe degradation of transfer performance. For BEV perception, we figure out the significant domain gaps existing in typical real-world cross-domain scenarios and comprehensively solve the Domain Adaption (DA) problem for multi-view 3D object detection. Since BEV perception approaches are complicated and contain several components, the domain shift accumulation on multiple geometric spaces (i.e., 2D, 3D Voxel, BEV) makes BEV DA even challenging. In this paper, we propose a Multi-space Alignment Teacher-Student (MATS) framework to ease the domain shift accumulation, which consists of a Depth-Aware Teacher (DAT) and a Geometric-space Aligned Student (GAS) model. DAT tactfully combines target lidar and reliable depth prediction to construct depth-aware information, extracting target domain-specific knowledge in Voxel and BEV feature spaces. It then transfers the sufficient domain knowledge of multiple spaces to the student model. In order to jointly alleviate the domain shift, GAS projects multi-geometric space features to a shared geometric embedding space and decreases data distribution distance between two domains. To verify the effectiveness of our method, we conduct BEV 3D object detection experiments on three cross-domain scenarios and achieve state-of-the-art performance. Code: https://github.com/liujiaming1996/BEVUDA.

Neuromorphic spike data, an upcoming modality with high temporal resolution, has shown promising potential in autonomous driving by mitigating the challenges posed by high-velocity motion blur. However, training the spike depth estimation network holds significant challenges in two aspects: sparse spatial information for pixel-wise tasks and difficulties in achieving paired depth labels for temporally intensive spike streams. Therefore, we introduce open-source RGB data to support spike depth estimation, leveraging its annotations and spatial information. The inherent differences in modalities and data distribution make it challenging to directly apply transfer learning from open-source RGB to target spike data. To this end, we propose a cross-modality cross-domain (BiCross) framework to realize unsupervised spike depth estimation by introducing simulated mediate source spike data. Specifically, we design a Coarse-to-Fine Knowledge Distillation (CFKD) approach to facilitate comprehensive cross-modality knowledge transfer while preserving the unique strengths of both modalities, utilizing a spike-oriented uncertainty scheme. Then, we propose a Self-Correcting Teacher-Student (SCTS) mechanism to screen out reliable pixel-wise pseudo labels and ease the domain shift of the student model, which avoids error accumulation in target spike data. To verify the effectiveness of BiCross, we conduct extensive experiments on four scenarios, including Synthetic to Real, Extreme Weather, Scene Changing, and Real Spike. Our method achieves state-of-the-art (SOTA) performances, compared with RGB-oriented unsupervised depth estimation methods. Code and dataset: https://github.com/Theia-4869/BiCross.

Visual language navigation (VLN) is an embodied task demanding a wide range of skills encompassing understanding, perception, and planning. For such a multifaceted challenge, previous VLN methods totally rely on one model’s own thinking to make predictions within one round. However, existing models, even the most advanced large language model GPT4, still struggle with dealing with multiple tasks by single-round self-thinking. In this work, drawing inspiration from the expert consultation meeting, we introduce a novel zero-shot VLN framework. Within this framework, large models possessing distinct abilities are served as domain experts. Our proposed navigation agent, namely DiscussNav, can actively discuss with these experts to collect essential information before moving at every step. These discussions cover critical navigation subtasks like instruction understanding, environment perception, and completion estimation. Through comprehensive experiments, we demonstrate that discussions with domain experts can effectively facilitate navigation by perceiving instruction-relevant information, correcting inadvertent errors, and sifting through in-consistent movement decisions. The performances on the representative VLN task R2R show that our method surpasses the leading zero-shot VLN model by a large margin on all metrics. Additionally, real-robot experiments display the obvious advantages of our method over single-round self-thinking. Our project web can be seen at the https://sites.google.com/view/discussnav.

Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However, the pursuit of long-term adaptation often introduces catastrophic forgetting and error accumulation problems, which impede the practical implementation of CTTA in the real world. Recently, existing CTTA methods mainly focus on utilizing a majority of parameters to fit target domain knowledge through self-training. Unfortunately, these approaches often amplify the challenge of error accumulation due to noisy pseudo-labels, and pose practical limitations stemming from the heavy computational costs associated with entire model updates. In this paper, we propose a distribution-aware tuning (DAT) method to make the semantic segmentation CTTA efficient and practical in real-world applications. DAT adaptively selects and updates two small groups of trainable parameters based on data distribution during the continual adaptation process, including domain-specific parameters (DSP) and task-relevant parameters (TRP). Specifically, DSP exhibits sensitivity to outputs with substantial distribution shifts, effectively mitigating the problem of error accumulation. In contrast, TRP are allocated to positions that are responsive to outputs with minor distribution shifts, which are fine-tuned to avoid the catastrophic forgetting problem. In addition, since CTTA is a temporal task, we introduce the Parameter Accumulation Update (PAU) strategy to collect the updated DSP and TRP in target domain sequences. We conducted extensive experiments on two widely-used semantic segmentation CTTA benchmarks, achieving competitive performance and efficiency compared to previous state-of-the-art methods.

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel space for supervision. However, the expensive annotation process and sometimes ambiguous labels have severely constrained the usability and scalability of 3D occupancy models. To address this, we present RenderOcc, a novel paradigm for training 3D occupancy models only using 2D labels. Specifically, we extract a NeRF-style 3D volume representation from multi-view images, and employ volume rendering techniques to establish 2D renderings, thus enabling direct 3D supervision from 2D semantics and depth labels. Additionally, we introduce an Auxiliary Ray method to tackle the issue of sparse viewpoints in autonomous driving scenarios, which leverages sequential frames to construct comprehensive 2D rendering for each object. To our best knowledge, RenderOcc is the first attempt to train multi-view 3D occupancy models only using 2D labels, reducing the dependence on costly 3D occupancy annotations. Extensive experiments demonstrate that RenderOcc achieves comparable performance to models fully supervised with 3D labels, underscoring the significance of this approach in real-world applications. Our code is available at https://github.com/pmj110119/RenderOcc.

While the integration of Multi-modal Large Language Models (MLLMs) with robotic systems has significantly improved robots’ ability to understand and execute natural language instructions, their performance in manipulation tasks remains limited due to a lack of robotics-specific knowledge. Conventional MLLMs are typically trained on generic image-text pairs, leaving them deficient in understanding affordances and physical concepts crucial for manipulation. To address this gap, we propose ManipVQA, a novel framework that infuses MLLMs with manipulation-centric knowledge through a Visual Question-Answering (VQA) format. This approach encompasses tool detection, affordance recognition, and a broader understanding of physical concepts. We curated a diverse dataset of images depicting interactive objects, to challenge robotic understanding in tool detection, affordance prediction, and physical concept comprehension. To effectively integrate this robotics-specific knowledge with the inherent vision-reasoning capabilities of MLLMs, we leverage a unified VQA format and devise a fine-tuning strategy. This strategy preserves the original vision-reasoning abilities while incorporating the newly acquired robotic insights. Empirical evaluations conducted in robotic simulators and across various vision task benchmarks demonstrate the robust performance of ManipVQA. The code and dataset are publicly available at https://github.com/SiyuanHuang95/ManipVQA.

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) insufficient reasoning ability to tackle complex tasks, and (2) high computational costs for VLA model fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an end-to-end robotic VLA model that leverages Mamba to deliver both robotic reasoning and action capabilities, while maintaining efficient fine-tuning and inference. Specifically, we first integrate the vision encoder with Mamba, aligning visual tokens with language embedding through co-training, empowering our model with visual common sense and robotic-related reasoning. To further equip RoboMamba with SE(3) pose prediction abilities, we explore an efficient fine-tuning strategy with a simple policy head. We find that once RoboMamba possesses sufficient reasoning capability, it can acquire manipulation skills with minimal fine-tuning parameters (0.1\% of the model) and time. In experiments, RoboMamba demonstrates outstanding reasoning capabilities on general and robotic evaluation benchmarks. Meanwhile, our model showcases impressive pose prediction results in both simulation and real-world experiments, achieving inference speeds 3 times faster than existing VLA models.

The task of Visual Object Navigation (VON) involves an agent's ability to locate a particular object within a given scene. To successfully accomplish the VON task, two essential conditions must be fulfiled: 1) the user knows the name of the desired object; and 2) the user-specified object actually is present within the scene. To meet these conditions, a simulator can incorporate predefined object names and positions into the metadata of the scene. However, in real-world scenarios, it is often challenging to ensure that these conditions are always met. Humans in an unfamiliar environment may not know which objects are present in the scene, or they may mistakenly specify an object that is not actually present. Nevertheless, despite these challenges, humans may still have a demand for an object, which could potentially be fulfilled by other objects present within the scene in an equivalent manner. Hence, this paper proposes Demand-driven Navigation (DDN), which leverages the user's demand as the task instruction and prompts the agent to find an object which matches the specified demand. DDN aims to relax the stringent conditions of VON by focusing on fulfilling the user's demand rather than relying solely on specified object names. This paper proposes a method of acquiring textual attribute features of objects by extracting common sense knowledge from a large language model (LLM). These textual attribute features are subsequently aligned with visual attribute features using Contrastive Language-Image Pre-training (CLIP). Incorporating the visual attribute features as prior knowledge, enhances the navigation process. Experiments on AI2Thor with the ProcThor dataset demonstrate that the visual attribute features improve the agent's navigation performance and outperform the baseline methods commonly used in the VON and VLN task and methods with LLMs. The codes and demonstrations can be viewed at https://sites.google.com/view/demand-driven-navigation.